© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6815
    Prev
    Next
    INDEX
    Explanations

    bibliography or appendices

    np_acts-logits-general · gemini-2.5-flash-lite

    resources and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     गुरूवार
    0.45
     inhe
    0.41
     गुरुवार
    0.41
    ClrBit
    0.41
    ashop
    0.39
    ensburg
    0.38
     Rotate
    0.37
    
    0.37
    üdis
    0.36
    বৃহস্পতিবার
    0.36
    POSITIVE LOGITS
     Bibliography
    2.50
     bibliography
    2.38
     References
    2.25
    Bibliography
    2.25
    References
    2.17
    REFERENCES
    2.09
     references
    2.02
     REFERENCES
    2.02
     appendices
    2.02
    bibliography
    2.00
    Activations Density 0.073%

    No Known Activations